COVID-19 Multi-Targeted Drug Repurposing Using Few-Shot Learning.
COVID-19 Multi-Targeted Drug Repurposing Using Few-Shot Learning.
复制标题
DOI：
10.3389/fbinf.2021.693177
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Xie, Lei
中科院分区：
文献类型：
--
作者：
Liu, Yang;Wu, You;Shen, Xiaoke;Xie, Lei
关键词：
威胁生命的疾病COVID-19激发了通过重新利用现有药物来发现新型治疗药物的重大努力。尽管多靶点（多药理学）疗法被公认为是治疗COVID-19等系统性疾病的最有效方法，但由于缺乏高质量的实验数据以及难以从分子中提取信息，计算多靶点化合物筛选一直受到限制。这项研究介绍了MolGNN，一种用于分子性质预测的新深度学习模型。MolGNN将图神经网络应用于化学分子嵌入的计算学习。与严重依赖标记实验数据的最先进方法相比，我们的方法在预训练阶段无需手动标记即可实现等同或上级的预测性能，并且在只有少量标记的数据上具有出色的性能。我们的研究结果表明，MolGNN对稀缺的训练数据具有鲁棒性，因此是一个强大的少次学习工具。MolGNN预测了几种针对人类Janus激酶和SARS-CoV-2主要蛋白酶的多靶向分子，这两种蛋白酶是分别旨在缓解细胞因子风暴COVID-19症状和抑制病毒复制的药物的优先靶点。我们还预测了可能抑制SARS-CoV-2诱导的细胞死亡的分子。现有的实验和临床证据支持MolGNN的几个顶级预测，证明了我们方法的潜在价值。
The life-threatening disease COVID-19 has inspired significant efforts to discover novel therapeutic agents through repurposing of existing drugs. Although multi-targeted (polypharmacological) therapies are recognized as the most efficient approach to system diseases such as COVID-19, computational multi-targeted compound screening has been limited by the scarcity of high-quality experimental data and difficulties in extracting information from molecules. This study introduces MolGNN, a new deep learning model for molecular property prediction. MolGNN applies a graph neural network to computational learning of chemical molecule embedding. Comparing to state-of-the-art approaches heavily relying on labeled experimental data, our method achieves equivalent or superior prediction performance without manual labels in the pretraining stage, and excellent performance on data with only a few labels. Our results indicate that MolGNN is robust to scarce training data, and hence a powerful few-shot learning tool. MolGNN predicted several multi-targeted molecules against both human Janus kinases and the SARS-CoV-2 main protease, which are preferential targets for drugs aiming, respectively, at alleviating cytokine storm COVID-19 symptoms and suppressing viral replication. We also predicted molecules potentially inhibiting cell death induced by SARS-CoV-2. Several of MolGNN top predictions are supported by existing experimental and clinical evidence, demonstrating the potential value of our method.
登录
查看更多内容
影响因子：
8.1
作者：
Hojyo S;Uchida M;Tanaka K;Hasebe R;Tanaka Y;Murakami M;Hirano T
通讯作者：
Hirano T
影响因子：
--
作者：
Chen, Xing;Liu, Ming-Xi;Yan, Gui-Ying
通讯作者：
Yan, Gui-Ying
影响因子：
7.4
作者：
Jin, Guangxu;Wong, Stephen T. C.
通讯作者：
Wong, Stephen T. C.
DOI：
10.1056/nejmra2026131
发表时间：
2020-12-03
期刊：
The New England journal of medicine
影响因子：
--
作者：
Fajgenbaum DC;June CH
通讯作者：
June CH
影响因子：
158.5
作者：
Beigel, John H.;Tomashek, Kay M.;Lane, H. Clifford
通讯作者：
Lane, H. Clifford